How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
AnthropicCLAUDE.mdanthropics/claude-cookbooks/claude_agent_sdk/chief_of_staff_agent/CLAUDE.md
Output: JSON with monthlyburn, runwaymonths, totalrunwaydollars, quarterlyburn, and burnrate_daily Remember: As Chief of Staff, you have access to financial data in the financial_data/ directory and can delegate specialized analysis to your subagents (financial-analyst and recruiter).
AnthropicCLAUDE.mdanthropics/claude-cookbooks/CLAUDE.md
A collection of Jupyter notebooks and Python examples for building with the Claude API. Or directly with uv: Notebooks have relaxed rules for mid-file imports (E402), redefinitions (F811), and variable naming (N803, N806). Branch naming: <username>/<feature-description> Commit format (conventional commits): These commands are available in Claude Code and CI:
AnthropicCLAUDE.mdanthropics/claude-cookbooks/skills/CLAUDE.md
This is a comprehensive Jupyter notebook cookbook demonstrating Claude's Skills feature for document generation (Excel, PowerPoint, PDF). It's designed for developers learning to integrate Skills into their applications. Beta API Requirements: - All Skills functionality uses client.beta.* namespace - Required beta headers: code-execution-2025-08-25, files-api-2025-04-14, skills-2025-10-02 - Must use client.beta.messages.create() with container parameter - Code execution tool (codeexecution20250825) is REQUIRED - Use pre-built Agent skills by referencing their skill_id or create and upload your own via the Skills API Files API…
AnthropicCLAUDE.mdanthropics/financial-services/CLAUDE.md
Cowork plugins and Claude Managed Agent templates for financial services. Each named agent ships two ways from one source. Run python3 scripts/check.py before committing — it lints every manifest, verifies all system.file / skills.path / callable_agents.manifest references resolve, fails if any agent-plugins/<slug>/skills/ copy has drifted from its vertical-plugins/ source, and rejects non-ASCII bytes in a .ps1 without a UTF-8 BOM. Keep .ps1 files pure ASCII. Windows PowerShell 5.1 — still the default shell on managed Windows — decodes a BOM-less…
AnthropicCLAUDE.mdanthropics/knowledge-work-plugins/partner-built/slack/CLAUDE.md
This plugin integrates Slack with Claude Code, providing tools to search, read, and send messages in Slack.
AnthropicCLAUDE.mdanthropics/claude-quickstarts/CLAUDE.md
No summary in the file. Open it to read it.
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/assistant-ui/CLAUDE.md
A Next.js chat app. assistant-ui renders everything; one Managed Agents session per conversation runs the analyst, and lib/managed-agents/reducer.ts folds each session's event log into the messages assistant-ui renders. The sidebar is the session list. There is no database. Needs Node 22+, @anthropic-ai/sdk 0.109.0 or later (event_deltas + session event helpers), and @assistant-ui/react 0.14.27 or later (the defineToolkit/Tools API and approvals on useExternalStoreRuntime). Pull exact shapes from the /claude-api skill's shared/managed-agents-*.md docs.
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/chat-sdk/CLAUDE.md
Long-running Node server (Hono): browser chat with a sessions sidebar (useChat → /api/chat) → Chat SDK web adapter onDirectMessage → one Managed Agents session per conversation, where the conversation ID is the session ID (no mapping, no database; the sidebar is sessions.list, transcript replay is sessions.events.list) → a held session event stream (opened with event_deltas token previews, always on) feeds each fragment back onto the same HTTP response while /api/activity streams the tool calls and thinking the page shows as…
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/copilot-kit-ag-ui/CLAUDE.md
A finance assistant chat app wiring a Claude Managed Agent to CopilotKit's self-hosted runtime over the AG-UI protocol. This file is the technical map: architecture, where the code is, design notes, and how to walk a user through setup. Four pieces:
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/daily-brief/CLAUDE.md
A scheduled deployment, not an app: there is no long-running process in this quickstart. agents/daily-brief/ holds six resource files that ant apply reconciles (agent, environment, two memory stores, vault, deployment). ant apply manages the vault container but never its contents, so agents/setup.sh adds the two credentials with ant beta:vaults:credentials create and writes the vault's ID into deployment.md's vaultids (a deployment takes vault IDs, not a file reference). Each scheduled run is a fresh session: it reads /mnt/memory/preferences/preferences.md (read-only store), reads…
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/knowledge-wiki/CLAUDE.md
This directory is a Managed Agents cookbook: it builds a real M&A data room into a knowledge wiki (a versioned memory store) and queries it. The runnable artifact is distilldocumentsintoknowledgewiki.ipynb; everything else exists to set that notebook up. When a user asks you to walk them through setting this quickstart up, read skill.md in this directory and follow it step by step. Do not improvise the setup — the SDK build, the SEC user-agent, and the fetch order all matter.
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/linear/CLAUDE.md
Stateless webhook bridge: Linear AgentSessionEvent → Managed Agents session (with routing metadata) → session.status_idled webhook → createAgentActivity reply. Pull exact shapes from the /claude-api skill's shared/managed-agents-*.md docs. Run the server with bun run dev. Agent provisioning is ant apply --yes agents environments from this directory (ant 1.30 or later; name the directories rather than ., and pass --yes because you have no terminal for its confirmation prompt, or --dry-run to show the plan first): it creates the agent and environment…
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/mcp-server-typescript/CLAUDE.md
MCP server that exposes Managed Agents session primitives as tools. Two entrypoints sharing one tool set: src/server.ts (stdio → Claude Desktop and Claude Code) and src/server-http.ts (Streamable HTTP → claude.ai custom connector). This quickstart creates no agents, so there is no agents/ directory. It needs one environment, created once from environment.yaml (the command is in that file and in README.md). Commands: bun run stdio (Desktop, Code), bun run http (claude.ai), bun run typecheck.
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/roadtrip-planner/CLAUDE.md
A Next.js chat built directly on a Managed Agent session: no chat framework, the event log is the app state. Teaches session event streaming (eventdeltas), vault credential injectionlocation, per-session agentwithoverrides, and multiagent coordinator rosters. The planner calls the National Park Service and Windy APIs with keys it never holds, then hands its draft to a second agent for a quick critique. That second agent is an Opus reviewer running as a session thread. 1. Invoke /claude-api first. It loads the…
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/self-hosted-sandboxes/CLAUDE.md
This file is the runbook for the three poller demos, docker/, docker-memory/, and archil/. The five webhook-started providers (cloudflare-containers/, cloudflare-worker/, daytona/, modal/, vercel/) share one agent and one environment, declared in webhook-demo/ and created with ant apply --yes . from that directory. Never run ant apply from this directory: it walks into the poller demos and creates their resources too, and the claude-lock.json it leaves here is then found first by every directory below. Each provider's README is its own…
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/sentry/CLAUDE.md
Scheduled deployment: cron → Managed Agents session with sentry-cli and a vault env-var credential → triage report in /mnt/session/outputs/. Pull exact shapes from the /claude-api skill's shared/managed-agents-*.md docs. Provisioning is ./agents/setup.sh (ant 1.34 or later, jq): it runs ant apply --yes agents environments vaults, which creates the agent, environment, and vault from those directories and records their IDs in claude-lock.json, then adds the Sentry token to the vault as an environmentvariable credential (skipped when the vault already has one), and…
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/slack/CLAUDE.md
Stateless webhook bridge: Slack appmention → Managed Agents session (with routing metadata) → session.statusidled webhook → chat.postMessage in-thread. Pull exact shapes from the /claude-api skill's shared/managed-agents-*.md docs. Run the server with bun run dev. Agent provisioning is ant apply --yes agents environments from this directory (ant 1.30 or later; name the directories rather than ., and pass --yes because you have no terminal for its confirmation prompt, or --dry-run to show the plan first): it creates the agent and environment…
AnthropicCLAUDE.mdanthropics/claude-for-legal/ai-governance-legal/CLAUDE.md
User-specific configuration for this plugin lives at a version-independent path that survives plugin updates: ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md Rules for every skill, command, and agent in this plugin: 1. READ configuration from that path. Not from this file. 2. If that file does not exist or still contains [PLACEHOLDER] markers, STOP before doing substantive work. Say: "This plugin needs setup before it can give you useful output. Run /ai-governance-legal:cold-start-interview — it takes about 10-15 minutes and every command in this plugin depends on…
AnthropicCLAUDE.mdanthropics/claude-for-legal/CLAUDE.md
Guidance for working on this repo. claude-for-legal is a Claude Code plugin marketplace — twelve first-party legal plugins, one vendor plugin, and five managed-agent cookbooks. Most work here is editing prompt content (skills, agents, hooks), plugin metadata, or cookbook config — not application code. This repo follows the same conventions anthropics/claude-plugins-official enforces in CI. Run the equivalent checks locally: claude-plugins-official layers these on top of the schema check. They apply here too — the ones most likely to trip a…
AnthropicCLAUDE.mdanthropics/claude-for-legal/commercial-legal/CLAUDE.md
User-specific configuration for this plugin lives at a version-independent path that survives plugin updates: ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md Rules for every skill, command, and agent in this plugin: 1. READ configuration from that path. Not from this file. 2. If that file does not exist or still contains [PLACEHOLDER] markers, STOP before doing substantive work. Say: "This plugin needs setup before it can give you useful output. Run /commercial-legal:cold-start-interview — it takes about 10-15 minutes and every command in this plugin depends on…
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
